Update of /cvsroot/python/python/dist/src/Lib
In directory usw-pr-cvs1:/tmp/cvs-serv8265/python/Lib
Modified Files:
gzip.py
Log Message:
Related to SF patch 618135: gzip.py and files > 2G.
Fixed the signed/unsigned confusions when dealing with files >= 2GB.
4GB is still a hard limitation of the gzip file format, though.
Testing this was a bitch on Win98SE due to frequent system freezes. It
didn't freeze while running gzip, it kept freezing while trying to *create*
a > 2GB test file! This wasn't Python's doing. I don't know of a
reasonable way to test this functionality in regrtest.py, so I'm not
checking in a test case (a test case would necessarily require creating
a 2GB+ file first, using gzip to zip it, using gzip to unzip it again,
and then compare before-and-after; so >4GB free space would be required,
and a loooong time; I did all this "by hand" once).
Bugfix candidate, I guess.
Index: gzip.py
===================================================================
RCS file: /cvsroot/python/python/dist/src/Lib/gzip.py,v
retrieving revision 1.35
retrieving revision 1.36
diff -C2 -d -r1.35 -r1.36
*** gzip.py 6 Aug 2002 17:03:25 -0000 1.35
--- gzip.py 4 Nov 2002 19:50:11 -0000 1.36
***************
*** 16,25 ****
READ, WRITE = 1, 2
def write32(output, value):
output.write(struct.pack("<l", value))
def write32u(output, value):
! if value < 0:
! value = value + 0x100000000L
output.write(struct.pack("<L", value))
--- 16,34 ----
READ, WRITE = 1, 2
+ def U32(i):
+ """Return i as an unsigned integer, assuming it fits in 32 bits.
+
+ If it's >= 2GB when viewed as a 32-bit unsigned int, return a long.
+ """
+ if i < 0:
+ i += 1L << 32
+ return i
+
def write32(output, value):
output.write(struct.pack("<l", value))
def write32u(output, value):
! # The L format writes the bit pattern correctly whether signed
! # or unsigned.
output.write(struct.pack("<L", value))
***************
*** 158,174 ****
if flag & FEXTRA:
# Read & discard the extra field, if present
! xlen=ord(self.fileobj.read(1))
! xlen=xlen+256*ord(self.fileobj.read(1))
self.fileobj.read(xlen)
if flag & FNAME:
# Read and discard a null-terminated string containing the filename
while True:
! s=self.fileobj.read(1)
! if not s or s=='\000': break
if flag & FCOMMENT:
# Read and discard a null-terminated string containing a comment
while True:
! s=self.fileobj.read(1)
! if not s or s=='\000': break
if flag & FHCRC:
self.fileobj.read(2) # Read & discard the 16-bit header CRC
--- 167,185 ----
if flag & FEXTRA:
# Read & discard the extra field, if present
! xlen = ord(self.fileobj.read(1))
! xlen = xlen + 256*ord(self.fileobj.read(1))
self.fileobj.read(xlen)
if flag & FNAME:
# Read and discard a null-terminated string containing the filename
while True:
! s = self.fileobj.read(1)
! if not s or s=='\000':
! break
if flag & FCOMMENT:
# Read and discard a null-terminated string containing a comment
while True:
! s = self.fileobj.read(1)
! if not s or s=='\000':
! break
if flag & FHCRC:
self.fileobj.read(2) # Read & discard the 16-bit header CRC
***************
*** 226,230 ****
def _read(self, size=1024):
! if self.fileobj is None: raise EOFError, "Reached EOF"
if self._new_member:
--- 237,242 ----
def _read(self, size=1024):
! if self.fileobj is None:
! raise EOFError, "Reached EOF"
if self._new_member:
***************
*** 287,292 ****
self.fileobj.seek(-8, 1)
crc32 = read32(self.fileobj)
! isize = read32(self.fileobj)
! if crc32%0x100000000L != self.crc%0x100000000L:
raise ValueError, "CRC check failed"
elif isize != self.size:
--- 299,304 ----
self.fileobj.seek(-8, 1)
crc32 = read32(self.fileobj)
! isize = U32(read32(self.fileobj)) # may exceed 2GB
! if U32(crc32) != U32(self.crc):
raise ValueError, "CRC check failed"
elif isize != self.size:
***************
*** 297,301 ****
self.fileobj.write(self.compress.flush())
write32(self.fileobj, self.crc)
! write32(self.fileobj, self.size)
self.fileobj = None
elif self.mode == READ:
--- 309,314 ----
self.fileobj.write(self.compress.flush())
write32(self.fileobj, self.crc)
! # self.size may exceed 2GB
! write32u(self.fileobj, self.size)
self.fileobj = None
elif self.mode == READ:
***************
*** 339,345 ****
raise IOError('Negative seek in write mode')
count = offset - self.offset
! for i in range(count/1024):
! self.write(1024*'\0')
! self.write((count%1024)*'\0')
elif self.mode == READ:
if offset < self.offset:
--- 352,358 ----
raise IOError('Negative seek in write mode')
count = offset - self.offset
! for i in range(count // 1024):
! self.write(1024 * '\0')
! self.write((count % 1024) * '\0')
elif self.mode == READ:
if offset < self.offset:
***************
*** 347,351 ****
self.rewind()
count = offset - self.offset
! for i in range(count/1024): self.read(1024)
self.read(count % 1024)
--- 360,365 ----
self.rewind()
count = offset - self.offset
! for i in range(count // 1024):
! self.read(1024)
self.read(count % 1024)
***************
*** 380,388 ****
def readlines(self, sizehint=0):
# Negative numbers result in reading all the lines
! if sizehint <= 0: sizehint = sys.maxint
L = []
while sizehint > 0:
line = self.readline()
! if line == "": break
L.append(line)
sizehint = sizehint - len(line)
--- 394,404 ----
def readlines(self, sizehint=0):
# Negative numbers result in reading all the lines
! if sizehint <= 0:
! sizehint = sys.maxint
L = []
while sizehint > 0:
line = self.readline()
! if line == "":
! break
L.append(line)
sizehint = sizehint - len(line)
RetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.4